Abstract
State-of-the-art image denoisers exploit various types of deep neural networks via deterministic training. Alternatively, very recent works utilize deep reinforcement learning for restoring images with diverse or unknown corruptions. Though deep reinforcement learning can generate effective policy networks for operator selection or architecture search in image restoration, how it is connected to the classic deterministic training in solving inverse problems remains unclear. In this work, we propose a novel image denoising scheme via Residual Recovery using Reinforcement Learning, dubbed R3L. We show that R3L is equivalent to a deep recurrent neural network that is trained using a stochastic reward, in contrast to many popular denoisers using supervised learning with deterministic losses. To benchmark the effectiveness of reinforcement learning in R3L, we train a recurrent neural network with the same architecture for residual recovery using the deterministic loss, thus to analyze how the two different training strategies affect the denoising performance. With such a unified benchmarking system, we demonstrate that the proposed R3L has better generalizability and robustness in image denoising when the estimated noise level varies, comparing to its counterparts using deterministic training, as well as various state-of the-art image denoising algorithms.
Original language | English |
---|---|
Title of host publication | 2021 IEEE International Conference on Image Processing (ICIP) |
Subtitle of host publication | Proceedings |
Place of Publication | Piscataway |
Publisher | IEEE |
Pages | 1624-1628 |
Number of pages | 5 |
ISBN (Electronic) | 978-1-6654-4115-5 |
ISBN (Print) | 978-1-6654-3102-6 |
DOIs | |
Publication status | Published - 2021 |
Event | 2021 IEEE International Conference on Image Processing (ICIP) - Virtual at Anchorage, United States Duration: 19 Sept 2021 → 22 Sept 2021 |
Conference
Conference | 2021 IEEE International Conference on Image Processing (ICIP) |
---|---|
Country/Territory | United States |
City | Virtual at Anchorage |
Period | 19/09/21 → 22/09/21 |
Bibliographical note
Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-careOtherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public
Keywords
- Training
- Recurrent neural networks
- Supervised learning
- Reinforcement learning
- Benchmark testing
- Search problems
- Robustness
- Recurrent Neural Network
- Deep Reinforcement Learning
- Image Denoising
- Residual Recovery